A Distributed Anytime Algorithm for Dynamic Task Allocation in Multi-Agent Systems

Macarthur, Kathryn; Stranders, Ruben; Ramchurn, Sarvapali D.; Jennings, Nicholas R.

doi:10.1609/aaai.v25i1.7866

Cited by 42 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, incomplete algorithms can be classified into local search, samplingbased and inference-based algorithms. Specifically, agents in local search algorithms such as DBA [16], DSA [22] and MGM [23] keep exchanging their own states (e.g., gains or assignments) with neighbors to iteratively optimize the solution. However, a major issue for local search algorithms is that they could potentially get trapped in local optima, since agents in them make their decision only based on the current preferred states of their neighbors.…”

Section: Related Workmentioning

confidence: 99%

“…However, as solving DCOPs is NP-hard, complete algorithms will incur exponential computational overheads, which limits their scalability. In contrast, incomplete algorithms [23,22,27,28], which may not necessarily find the optimal solution, are considered more efficient to apply to large-scale real-world problems.…”

mentioning

confidence: 99%

“…As a version of belief propagation approach [44], Max-sum [11] and its variants are important incomplete algorithms for DCOPs based on the Generalized Distributive Law (GDL) [1], which have been widely applied to solve many real-world coordination problems such as sensor networks [10,35] and task allocation [8,22]. However, for n-ary problems, they suffer from a huge challenge of scalability.…”

mentioning

confidence: 99%

“…To alleviate this issue, many efforts have been made to speed up the maximization operation in Max-sum to improve their scalability for n-ary problems. To date, the existing acceleration methods can be categorized into BnB-based ones [22,39] and sorting-based ones [18,9]. The former employ a branch-andbound to prune the search space, while the latter require (partially) sorted local function utilities to perform acceleration.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Toward Fast Belief Propagation for Distributed Constraint Optimization Problems via Heuristic Search⋆

Gao

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Belief propagation (BP) approaches, such as Max-sum and its variants , are important methods to solve large-scale Distributed Constraint Optimization Problems (DCOPs). However, these algorithms face a huge challenge since their computational complexity scales exponentially with the arity of each constraint function. Current accelerating techniques for BP use sorting or branch-and-bound (BnB) strategy to reduce the search space. However, the existing BnB-based methods are mainly designed for specific problems, which limits their applicability. On the other hand, though several generic sorting-based methods have been proposed, they require significantly high preprocessing as well as memory overhead, which prohibits their adoption in some realistic scenarios. In this paper, we aim to propose a series of generic and memory-efficient heuristic search techniques to accelerate belief propagation. Specifically, by leveraging dynamic programming, we efficiently build function estimations for every partial assignment scoped in a constraint function in the preprocessing phase. Then, by using these estimations to build upper bounds and employing a branch-and-bound in a depth-first fashion to reduce the search space, we propose our first method called FDSP. Next, we enhance FDSP by adapting a concurrent-search strategy and leveraging the upper bounds as guiding information and propose its first heuristic variant framework called CONC-FDSP. Finally, by choosing to expand the partial assignment with the highest upper bound in each step of exploration, we propose the second heuristic variant of FDSP, called BFS-FDSP. We prove the correctness of our methods theoretically, and our empirical evaluations indicate their superiority for accelerating Max-sum in terms of both time and memory, compared with the state-of-the-art.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Toward Fast Belief Propagation for Distributed Constraint Optimization Problems via Heuristic Search⋆

Gao

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To solve this problem, researchers have achieved a series of research results around coalition structure (Voice et al, 2012;Zick et al, 2014), coalition clustering (Kashef & Kamel, 2010), solving algorithm (Macarthur et al, 2011), and formed a certain theoretical and technical foundation.…”

Section: Introductionmentioning

confidence: 99%

A Survey of UAV Swarm Task Allocation Based on the Perspective of Coalition Formation

Wu¹,

Peng²,

Shi³

et al. 2022

International Journal of Swarm Intelligence Research

View full text Add to dashboard Cite

Coalition formation of unmanned aerial vehicle (UAV) swarms, an effective solution for UAV swarm task allocation, is an important technology for UAV swarms to perform real-time and efficient collaborative task allocation in a dynamic and unknown environment. This paper summarizes the task allocation methods of UAV swarm coalition comprehensively and systematically. First, starting with the related work of UAV swarm coalition task allocation, this paper introduces the basic concept, general model, and constraint index of UAV swarm coalition task allocation. Then, the specific content, research status, advantages, and disadvantages of the coalition formation methods are analyzed, respectively. Third, the commonly used solution algorithms and research status of coalition task allocation are introduced, and the advantages and disadvantages of the existing coalition formation solution algorithms are compared and analyzed. Finally, it provides significant guidance for future related research.

show abstract

A negotiation‐based method for task allocation with time constraints in open grid environments

Kong

Zhang

2014

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThis paper addresses the task allocation problem in an open, dynamic grid environments and service‐oriented environments. In such environments, both grid/service providers and consumers can be modelled as intelligent agents. These agents can leave and enter the environment freely at any time. Task allocation under time constraints becomes a challenging issue in such environments because it is difficult to apply a central controller during the allocation process due to the openness and dynamism of the environments. This paper proposes a negotiation‐based method for task allocation under time constraints in an open, dynamic grid environment, where both consumer and provider agents can freely enter or leave the environment. In this method, there is no central controller available, and agents negotiate with each other for task allocation based only on local views. The experimental results show that the proposed method can outperform the current methods in terms of the success rate of task allocation and the total profit obtained from the allocated tasks by agents under different time constraints. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

A Distributed Anytime Algorithm for Dynamic Task Allocation in Multi-Agent Systems

Cited by 42 publications

References 6 publications

Toward Fast Belief Propagation for Distributed Constraint Optimization Problems via Heuristic Search⋆

Toward Fast Belief Propagation for Distributed Constraint Optimization Problems via Heuristic Search⋆

A Survey of UAV Swarm Task Allocation Based on the Perspective of Coalition Formation

A negotiation‐based method for task allocation with time constraints in open grid environments

Contact Info

Product

Resources

About